基于自编码器和LSTM的模型降阶方法

武频; 孙俊五; 封卫兵

doi:10.7638/kqdlxxb-2019.0082

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于自编码器和LSTM的模型降阶方法

研究论文 | 更新时间：2026-05-28

- 基于自编码器和LSTM的模型降阶方法
- Reduced order model based on autoencoder and long short-term memory network
- 空气动力学学报 2021年39卷第1期页码：73-81
- 作者机构：
  
  上海大学计算机工程与科学学院,上海,200444
- 作者简介：
  
  武频(1975-), 女, 河北人, 副教授, 研究方向: CFD数值计算, 大数据分析与应用.E-mail: wupin@shu.edu.cn
- 基金信息：
  
  上海市自然科学基金（19ZR1417700）;空气动力学国家重点实验室开放课题（SKLA20180303）
- DOI：10.7638/kqdlxxb-2019.0082
  中图分类号： TP181;V211.3
- 纸质出版：2021
- 稿件说明：
移动端阅览
武频, 孙俊五, 封卫兵. 基于自编码器和LSTM的模型降阶方法[J]. 空气动力学学报, 2021, 39(1): 73-81.

WU Pin, SUN Junwu, FENG Weibing. Reduced order model based on autoencoder and long short-term memory network[J]. 2021, 39(1): 73-81.
武频, 孙俊五, 封卫兵. 基于自编码器和LSTM的模型降阶方法[J]. 空气动力学学报, 2021, 39(1): 73-81. DOI： 10.7638/kqdlxxb-2019.0082.

WU Pin, SUN Junwu, FENG Weibing. Reduced order model based on autoencoder and long short-term memory network[J]. 2021, 39(1): 73-81. DOI： 10.7638/kqdlxxb-2019.0082.

摘要

自编码器是一种有效的数据降维方法，可以学习到数据中的隐含特征，并重构出原始输入数据。本文提出了一种基于多层自编码器和长短期记忆网络的模型降阶方法，以提升降阶模型的精度。文中以二维圆柱绕流为例，对该方法进行了分析与验证。首先用多层自编码器对原始数据进行降阶和特征提取，然后构建基于长短期记忆网络的预测模型，最后将自编码器和预测模型拼接并进行微调，得到降阶模型，并将其与基于主成分分析的降阶模型进行对比。结果表明，多层自编码器能在保证精度的同时提升数据压缩率；提出的降阶方法有效地提升了模型精度，使得预测速度场和原速度场之间的均方根误差降低至3×10

-3

左右。

Abstract

Autoencoder is an effective dimensionality reduction method that can learn the hidden information and features implicated in the data

and reconstruct the original input data. We propose a model reduction method with improved accuracy based on a multi-layer autoencoder and a long short-term memory network. The method is analyzed and verified through a two-dimensional flow past a cylinder. Firstly

the multi-layer autoencoder is used to reduce the order and extract features of the original data. Then

a prediction model based on a long short-term memory network is established. At last

the autoencoder and the prediction model are spliced into a single network to obtain a fine-tuned reduced order model. This model is further c

ompared with another one based on the principal component analysis. Results show that the multi-layer autoencoder can improve the data compression ratio while ensuring the accuracy. The proposed reduced order method can effectively improve the model accuracy since the root mean square error between the predicted and the original velocity fields is reduced to within 3×10

-3

关键词

Keywords

references

DOWELL E H. Eigenmode analysis in unsteady aerodynamics-Reduced-order models[J]. Applied Mechanics Reviews, 1997, 50(6): 371.

SILVA W A. Identification of linear and nonlinear aerodynamic impulse responses using digital filter techniques: AIAA-97-3712[R]. Reston: AIAA, 1997.

CHEN G, LI Y M. Advances and prospects of the reduced order model for unsteady flow and itsapplication[J]. Advances in Mechanics, 2011, 41(6): 686-701. (in Chinese)

LIBBRECHT M W, NOBLE W S. Machine learning applications in genetics and genomics[J]. Nature Reviews Genetics, 2015, 16(6): 321.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. 2012: 1097-1105.

KOUROU K, EXARCHOS T P, EXARCHOS K P, et al. Machine learning applications in cancer prognosis and prediction[J]. Computational and Structural Biotechnology Journal, 2015, 13: 8-17.

KUTZ J N. Deep learning in fluiddynamics[J]. Journal of Fluid Mechanics, 2017, 814: 1-4.

ZHANG W W, ZHU L Y, LIU Y L, et al. Progresses in the application of machine learning in turbulence modeling[J]. Acta Aerodynamica Sinica, 2019, 37(3): 444-454. (in Chinese)

TOMPSON J, SCHLACHTER K, SPRECHMANN P, et al. Accelerating eulerian fluid simulation with convolutional networks[C]//34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017: 3424-3433.

WANG Q, HESTHAVEN J S, RAY D. Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem[J]. Journal of Computational Physics, 2019, 384: 289-307.

HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.

MANNARINO A, MANTEGAZZA P. Nonlinearaeroelastic reduced order modeling by recurrent neural networks[J]. Journal of Fluids and Structures, 2014, 48: 103-121.

WANG Z, XIAO D, FANG F, et al. Model identification of reduced order fluid dynamics systems using deep learning[J]. International Journal for Numerical Methods in Fluids, 2018, 86(4): 255-268.

GRAVES A, SCHMIDHUBER J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks, 2005, 18(5-6): 602-610.

LINDHORST K, HAUPT M C, HORST P. Efficient surrogate modelling of nonlinear aerodynamics inaerostructural coupling schemes[J]. AIAA Journal, 2014, 52(9): 1952-1966.

YAO W, MARQUES S. Nonlinear aerodynamic andaeroelastic model reduction using a discrete empirical interpolation method[J]. AIAA Journal, 2017, 55(2): 1-14.

YIN M L, KOU J Q, ZHANG WW. A reduced-order aerodynamic model with high generalization capability based on neural network[J]. Acta Aerodynamica Sinica, 2017, 35(2): 205-213. (in Chinese) doi: 10. 7638/kqdlxxb-2015. 0210

KOU J, ZHANG W. Multi-kernel neural networks for nonlinear unsteady aerodynamic reduced-order modeling[J]. Aerospace Scienceand Technology, 2017, 67: 309-326.

RUMELHART D E, HINTON G E, WILLIAMS R J. Learning internal representations by error propagation[R]. California Univ San Diego La Jolla Inst for Cognitive Science, 1985.

YE S R, ZHANG Z, SONG X D, et al. Applications of autoencoder in reduced-order modeling of flow field[J]. Acta Aerodynamica Sinica, 2019, 37(3): 498-504. (in Chinese) doi: 10. 7638/kqdlxxb-2019. 0039.

HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep beliefnets[J]. Neural Computation, 2006, 18(7): 1527-1554.

KINGMA D P, BA J. Adam: a method for stochastic optimization[J]. ArXiv Preprint ArXiv: 1412. 6980, 2014.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于LBM方法的LAGOON起落架噪声预测与降噪方法研究

风扇叶片颗粒侵蚀特性的多因素分析与模拟

基于Ac-准则的最优输入设计方法

类HyTRV升力体阻尼/交叉动导数特性分析

水滴撞击运动超疏水表面特性及其调控